New programForward Deployed Engineering Program (FDE) starts 5 December 2026. Registrations are open.FDE starts 5 Dec 2026Apply now
All programs
Flagship programStarts 5 Dec 2026

Forward Deployed
Engineering.
Own the outcome.

Forward Deployed Engineering Practitioner Program

Become the engineer who takes AI from a promising prototype to a working system inside a real organisation.

What an FDE blends3 roles
AnalystFrame it.Discovery + scopingEngineerBuild it.AI + softwareDevOpsShip it.Deploy + monitorFDE
Three roles. One engineer.
24Sessions
1Connected engagement
HybridOnline + optional campus immersions
IIT HyderabadFaculty-led program

A new chapter starts here.

Enrolling now5 December 2026 to 14 March 2027

Online learning with three optional campus immersions at IIT Hyderabad.

  • Campus Immersion 1 5 December 2026
  • Campus Immersion 2 9 January 2027
  • Campus Immersion 3, Capstone Presentations and Convocation 13–14 March 2027

Revised schedule: At participants’ request, no sessions will be held during the Christmas and Sankranti weeks (26 December 2026 and 16 January 2027). The programme now concludes on 14 March 2027.

See the schedule

What you will be able to do

01

Discover the real problem

Map the customer workflow, constraints and success measures before choosing the technology.

02

Engineer the complete system

Build services, data flows, AI workflows and enterprise integrations in one engagement.

03

Own deployment and adoption

Release safely, operate reliably and connect user adoption to measurable business value.

Who joins this program

Bring your engineering foundation. Build towards delivery ownership, from understanding a customer’s problem to deploying and handing over a working AI solution.

Software Engineers

Moving from building features to owning AI delivery with customers.

AI / ML & Data Engineers

Who can build models, pipelines and prototypes, and want them running in production.

Platform, DevOps & Analyst

Hands-on technologists stepping into customer-facing AI delivery.

Teams from one company

Taking AI pilots to production together. [Team terms]

Typical experience: 2 to 3+ years
Python

Write, read and debug app code; packages, exceptions, structured data.

APIs & Services

HTTP, REST and JSON; FastAPI and Pydantic.

Databases

SQL, tables, keys and basic transactions in Postgres.

Engineering Workflow

Git, Linux terminal, dependencies, existing repos.

Testing & Containers

Basic pytest; running a containerised app.

A deployment you can explain. Evidence you can show.

Every lab adds to one engagement repository, from customer discovery to operational handover.

01

Discovery & scope

Customer brief, workflow map, requirements, risks and an outcome hypothesis.

02

Engineering foundation

Reproducible repository, typed service, versioned API, data layer, tests and CI.

03

Enterprise intelligence

Integrations, event processing, model routing, retrieval and agent workflows with human control.

04

Operational product

Role-aware operator interface, deployment architecture, enterprise identity and network fit.

05

Production evidence

Tracing, service-level objectives, evaluation harness, threat model and failure exercises.

06

Forward deployment

Staged rollout, adoption and value measurement, handover, executive readout and postmortem.

The capstone connects the customer workflow, architecture, integrations, failure modes, evaluation, operations, adoption and business outcomes. A chat interface alone does not meet the engagement standard.

One engagement.
Every layer of delivery.

Each module adds evidence to the same engagement repository. The curriculum is a draft; the session-to-date mapping is being finalised.

24 sessions, guided labs and a capstone

01
SESSIONS 01–02

Models and agent harnesses

Model, reasoning, context and gateway engineering. Agent harness, skills and engineering velocity.

02
SESSIONS 03–04

Retrieval and knowledge engineering

Advanced retrieval strategies. Knowledge bases, knowledge graphs and GraphRAG.

03
SESSIONS 05–06

Loop and graph engineering

Loop engineering. Graph engineering and adaptive agent topologies.

04
SESSIONS 07–08

Memory, evaluation and optimisation

Memory and long-context engineering. Agent evaluation and neuro-symbolic verification.

05
SESSIONS 09–10

Enterprise context and governed data access

Enterprise data discovery and agent-ready access. Enterprise context, semantics and ontology engineering.

06
SESSIONS 11–12

AI-native data engineering and storage

Intelligent multimodal ingestion and data contracts. AI storage architecture and knowledge lifecycle.

07
SESSIONS 13–14

Enterprise SQL agents and AI analytics

Semantic-layer-grounded SQL agents. Analytical intelligence across structured and unstructured data.

08
SESSIONS 15–16

Enterprise capability integration and proactive AI workflows

Agent-ready enterprise APIs, MCP and connectors. Event-driven, proactive and recoverable agent workflows.

09
SESSIONS 17–18

AI operations, controlled pilots and safe releases

Observability, continuous quality and AI FinOps. Progressive autonomy, model migration and safe releases.

10
SESSIONS 19–20

Identity, trusted execution and security

Enterprise identity and agent authorisation. Agentic security and AI supply chain.

11
SESSIONS 21–22

Model serving and operational applications

Model selection, optimisation and serving. Deployable AI applications and agent-to-user interfaces.

12
SESSIONS 23–24

Distributed AI systems and scaling

Scaling and isolating agent workloads. Distributed inference and capacity engineering.

One engagement.
Every layer of delivery.

Over 9 weeks, you build one customer AI engagement, from problem discovery to a tested deployment, user acceptance and handover. Each week adds to the same engagement repository.

24 sessions3 phases1 capstone
Phase 1, BuildEngineer intelligent AI systemsWeeks 1–4
Sessions 01–08
Week 01, sessions 01–02Models and agent harnesses
  • S01: Model, reasoning, context and gateway engineering

    Fast vs deliberative models, structured outputs, context budgeting and compaction, caching, model routing, cost and provider abstraction.

  • S02: Agent harness, skills and engineering velocity

    Pi, AGENTS.md, SKILL.md, plugins, progressive disclosure, Superpowers, SDD/TDD, independent review and sandboxed execution.

Week 02, sessions 03–04Retrieval and knowledge engineering
  • S03: Advanced retrieval strategies

    Document AI, multimodal parsing, lexical, vector and hybrid search, reranking, hierarchical and vectorless retrieval, provenance, citations and abstention.

  • S04: Knowledge bases, knowledge graphs and GraphRAG

    Entities, relationships, ontologies, small-scale graph construction, multi-hop reasoning, temporal facts and graph-assisted retrieval.

Week 03, sessions 05–06Loop and graph engineering
  • S05: Loop engineering

    ReAct, plan-act-verify, bounded goal loops, heartbeat, schedule and event triggers, tool permission boundaries, budget limits, stuck detection, retry, pivot, escalation and termination.

  • S06: Graph engineering and adaptive agent topologies

    LangGraph state, deterministic and validator nodes, conditional edges, checkpointing, human interrupts, parallel delegation, static vs adaptive graphs and A2A concepts.

Week 04, sessions 07–08Memory, evaluation and optimisation
  • S07: Memory and long-context engineering

    Working, episodic, semantic and procedural memory, consolidation, compaction, contradiction handling, revision, expiry, deletion and poisoning defence.

  • S08: Agent evaluation and neuro-symbolic verification

    Task and trajectory evaluation, calibrated judges, tool-action correctness, property testing, deterministic invariants, Z3 constraints and evaluation-driven optimisation (GEPA).

Phase 2, ConnectIntegrate enterprise data and systemsWeeks 5–8
Sessions 09–16
Week 05, sessions 09–10Enterprise context and governed data access
  • S09: Enterprise data discovery and agent-ready access

    Data estates, metadata discovery, ownership, lineage, permissions, catalogues, APIs, databases, warehouse access and synthetic data environments.

  • S10: Enterprise context, semantics and ontology engineering

    Canonical entities, cross-system identity mapping, business vocabularies, semantic metrics, entity relationships, source precedence and knowledge provenance, with an introduction to Apache Ossie and metadata-aware AI.

Week 06, sessions 11–12AI-native data engineering and storage
  • S11: Intelligent multimodal ingestion and data contracts

    LLM-powered extraction, classification and enrichment, deterministic transformations, schema validation, AI data contracts, exception handling, lineage, freshness and deletion propagation.

  • S12: AI storage architecture and knowledge lifecycle

    Relational, vector and graph stores, lakehouse and warehouse integration, indexing strategies, tenant-aware filtering, incremental updates, re-embedding, versioning, retention and safe migrations.

Week 07, sessions 13–14Enterprise SQL agents and AI analytics
  • S13: Semantic-layer-grounded SQL agents

    Metadata-guided schema discovery, business metric definitions, text-to-SQL, query decomposition, SQL AST validation, schema and column authorisation, read-only execution, query budgets and execution-accuracy evaluation.

  • S14: Analytical intelligence across structured and unstructured data

    Multi-step analytical planning, sandboxed Python computation, warehouse and lakehouse access, graph, SQL and vector reasoning, source attribution, numerical reconciliation and analytical evaluation.

Week 08, sessions 15–16Enterprise capability integration and proactive AI workflows
  • S15: Agent-ready enterprise APIs, MCP and connectors

    Converting existing APIs into safe agent capabilities, OpenAPI-to-MCP adaptation, skills and plugins, typed tool contracts, scoped permissions, approval-bound actions, idempotency and connector governance, with an introduction to browser and computer-use fallback.

  • S16: Event-driven, proactive and recoverable agent workflows

    Webhooks, schedules, CDC, event-triggered loops, asynchronous execution, knowledge freshness, duplicate events, retries, dead-letter handling and recovery.

Phase 3, ShipSecure, deploy, operate and demonstrate valueWeeks 9–12
Sessions 17–24
Week 09, sessions 17–18AI operations, controlled pilots and safe releases
  • S17: Observability, continuous quality and AI FinOps

    OpenTelemetry and OpenObserve, model, agent and tool traces, task quality, drift, cost per successful task, tenant and feature attribution, budgets, SLOs and FOCUS-aligned cost reporting.

  • S18: Progressive autonomy, model migration and safe releases

    Shadow, human-approved and scoped autonomous execution, OpenFeature and flagd, evaluation-based canaries, prompt, model and skill versioning, rollback, release manifests, technical UAT and incident recovery.

Week 10, sessions 19–20Identity, trusted execution and security
  • S19: Enterprise identity and agent authorisation

    OIDC, SAML and SCIM, authentik, scoped and delegated credentials, user-to-tool attribution, MCP authorisation, enterprise-managed authorisation, RBAC and ReBAC, and gateway policy controls.

  • S20: Agentic security and AI supply chain

    OWASP LLM, agentic and MCP risks, malicious skills and plugins, memory poisoning, tool escalation, sandbox boundaries, PII, model provenance, approved capabilities and AI bills of materials.

Week 11, sessions 21–22Model serving and operational applications
  • S21: Model selection, optimisation and serving

    Hosted vs self-hosted models, sovereign and Indian-language options, prompt optimisation, RAG vs fine-tuning, quantisation, KV caching, batching, vLLM and inference economics.

  • S22: Deployable AI applications and agent-to-user interfaces

    Production service topology, durable execution, containers, AG-UI, MCP Apps, streaming progress, human approvals, exception handling and managed vs self-hosted runtimes.

Week 12, sessions 23–24Distributed AI systems and scaling
  • S23: Scaling and isolating agent workloads

    Stateless services vs durable state, workers, Kubernetes pods, queues, KEDA, safe code execution, sandbox isolation, resource limits and failure recovery.

  • S24: Distributed inference and capacity engineering

    Model-aware routing, KV cache reuse and offloading, disaggregated inference, SGLang, llm-d, Dynamo, residency, availability and cost-capacity architecture.

Alongside the weekend sessions, industry leader talks and doubt-clarification sessions will be held on pre-informed weekdays.

The curriculum and schedule are subject to enhancements. A few modules, topics or their sequence may change as the programme is enriched, while retaining the core learning objectives.

The journey, on your calendar.

Tentative
Week 1Program beginsCampus Immersion 1 (optional)
Weeks 2–4Phase 1, BuildOnline learning
Week 5Phase 2, Connect beginsCampus Immersion 2 (optional)
Weeks 6–8Phase 2, ConnectOnline learning
Weeks 9–12Phase 3, ShipOnline learning
13–14 Mar 2027Capstone presentations and convocationCampus Immersion 3 (optional)

At participants’ request, no sessions will be held during the Christmas and Sankranti weeks (26 December 2026 and 16 January 2027).

Webinars

Free online sessions on what Forward Deployed Engineering is and how the program works.

CompletedFDE Webinar 2

Inside Forward Deployed Engineering

Thursday, 12 November 2026 7:00 to 8:00 PM IST Online
  • From messy requirements to a working AI solution
  • Real customer problems
  • AI-assisted engineering
  • A delivery mindset
Open in a new tab
CompletedFDE Webinar 1

Understanding what FDE means

14 October 2026 7:00 PM IST Online
  • What a Forward Deployed Engineer does
  • Why the AI job market needs this skill set
  • A look at the FDE Practitioner Program

Our instructors

Inside the classroom

Questions, conversations and the quiet satisfaction of making something work.

FDE Practitioner Program certificate preview

Evidence you can stand behind.

Certificate details and completion requirements will be announced with the final program release.

  • A customer brief and architecture decisions
  • Working software, integrations and operational evidence
  • A rollout, adoption and handover portfolio

The final certificate title, issuer details and assessment criteria are to be confirmed.

Start with a conversation.

Registration for the December program is open. Use the registration form or contact the team with questions.

Open December registration form Enquire on this page Google Forms opens in a new tab. Form availability is managed by the program team.

Take ownership of what AI can do.

For AI engineers and software engineers with roughly 2–5 years of experience, moving into customer-facing AI delivery.

Before you begin

Working programming skills, API familiarity and readiness to build and review software. This is a practitioner program, not a first course in coding.

Earlybird Price: ₹90,000 + taxesLimited seats
Standard Price

₹1,00,000 + taxes

Early-bird price applies to the first 20 registrations.

EMI available in 3 instalments, from ₹53,100
  1. Instalment 1₹53,100₹45,000 + ₹8,100 GST
  2. Instalment 2₹32,450₹27,500 + ₹4,950 GST
  3. Instalment 3₹32,450₹27,500 + ₹4,950 GST

Total ₹1,18,000 including GST, on the standard price.

Pay by EMI on BillDesk

Runs from 5 December 2026 to 14 March 2027.

  • All sessions, guided labs and 3 optional campus immersions
  • IIT Hyderabad certificate
Enquire about the program Speak to the team on WhatsApp Corporate group registrations are eligible for additional discounts. Contact us to check eligibility and avail discounted pricing.

Good questions.
Straight answers.

Ask us something else
What does a Forward Deployed Engineer do?

Works with customers to understand a business problem and deliver a working solution, combining AI and software engineering with discovery, integration, deployment and stakeholder communication.

Do I need prior GenAI experience, and which technologies will I use?

No prior GenAI or ML experience is needed, only solid software engineering foundations (see Eligibility). You will learn LLMs, retrieval, agents and evaluation hands-on, using a Python-first, open-source stack that includes FastAPI, Postgres, LangGraph, Qdrant, Ragas, authentik, Docker, OpenTelemetry and OpenObserve.

Is it relevant for cybersecurity, DevOps, data or integration professionals?

Yes, if your role is hands-on and you meet the prerequisites. Identity, secure integrations, data pipelines, deployment and observability are core to the curriculum.

What will I build?

A team capstone: an enterprise AI workflow with evidence retrieval, human approval and an audit trail, taken from discovery through deployment and handover.

Do I need paid AI subscriptions?

No. The required labs use programme-provided scripts and free tiers. Optional experimentation outside this may cost extra.

How will I be assessed?

Through working software, tests, evaluation results, architecture and security evidence, and a capstone presentation where you defend your decisions. Certificate requirements will be announced separately.

How long is the programme, and can I attend while working full-time?

Yes, the programme is designed for working professionals. It runs for 13 weeks, including 12 weeks of lectures with 24 sessions and 72 live hours. Each session combines a 90-minute lecture with a 90-minute hands-on lab. Plan for about 9 live hours a week: 6 hours of sessions plus about 3 hours of industry lectures and doubt-clarification sessions, along with independent time for preparation and the capstone.