Technology & Intelligence Ref XE-TEC-203 Open

AI Engineer, Agents & RAG

Build AI agents and retrieval pipelines for client products, and show they work with evaluation sets, safety checks, approval steps and production monitoring.

Illustrative role: we confirm the details before it opens.

Apply for this role See how we hire
Share Email it
Two engineers at a desk discussing code on a monitor, one leaning over the other's shoulder.
The practiceTechnology & Intelligence
Practice
Technology & Intelligence
Location
New Delhi
Work pattern
Hybrid
Level
Mid–Senior
Type
Full-time
Experience
3+ years
Salary band
₹22–36 lakh a year Indicative
Openings
2
Posted
Closes
37 days left

About the role

You will build the tools, retrieval pipelines and agent workflows behind our clients’ AI products.

An agent is ready for release when it passes an evaluation suite for grounding, accuracy and safety. It must also resist prompt injection (OWASP LLM01) and data leakage. A named person approves the actions that matter, and you track cost, latency and quality in production.

What you will do

  1. Design retrieval pipelines, tools and agent workflows
  2. Write evaluation suites for grounding, accuracy and safety, and run them on every change
  3. Build automatic checks against prompt injection and data leakage
  4. Add a named approver wherever an agent takes an action that matters
  5. Instrument cost, latency and quality in production

A typical week

How the hours split in a typical week. Agents draft and check some tasks; you decide what happens next.

AI Engineer, Agents & RAG 40 hours in a typical week
  • You14 h · 35%
  • You, with an agent drafting20 h · 50%
  • An agent runs it, you review6 h · 15%

  1. Retrieval pipelines and agent workflows

    A coding assistant drafts; you design, test and decide.

    You, with an agent drafting12 h

  2. Writing and running evaluations

    You write the cases; agents run the suites on every change and summarise what failed.

    You, with an agent drafting8 h

  3. Safety checks and red-team tests

    Testing for prompt injection (OWASP LLM01) and data leakage, plus approval steps for actions that matter.

    You6 h

  4. Production monitoring

    Dashboards and alerts watch cost, latency and quality; you investigate what they flag.

    An agent runs it, you review6 h

  5. Design reviews and client sessions

    Reviewing designs and code, and explaining results to clients.

    You8 h

An illustrative split. In your first conversation, the hiring lead talks you through how the week runs.

What you bring

  • 3+ years of software engineering, including 1+ year releasing features built on large language models
  • Python and one vector store in production
  • A working understanding of the OWASP Top 10 for LLM Applications
  • Evidence that you measure quality rather than eyeball it

Nice to have

  • Fine-tuning or small-model deployment
  • Experience in regulated industries

None of this is required. If you have most of the list above, apply.

Tools you will use

Grouped by purpose. Nobody knows all of them on day one.

Languages & runtimes
  • Python
Backend & APIs
  • FastAPI
Model providers
  • Anthropic
  • OpenAI
Agents, retrieval & evaluation
  • LangGraph
  • LlamaIndex
  • pgvector
  • Qdrant
Containers, IaC & CI/CD
  • Docker
Observability
  • OpenTelemetry

Tools we work with and license. No partnership is implied.

Your first 90 days

  1. Days 1–30

    Extend a live agent’s evaluation suite and fix the first failure it finds

  2. Days 31–60

    Release a retrieval improvement with before-and-after evaluation scores

  3. Days 61–90

    Own an agent workflow in production: its safety checks, dashboards and approval steps

A hand-drawn goal review on dot-grid paper: tallies for weeks one to eleven beside an assess-and-plan column, two pens resting on the page.
The plan is written down before your first day, and you review it with your lead as the weeks go by.

Where you would work

Where this role can be based. Each team agrees its own office days; remote roles join a team week in an office each quarter.

  • Auto rickshaws on a wide avenue in New Delhi, the dome of Rashtrapati Bhavan at the end of the road in evening haze.

    Office

    New Delhi

    Office at Aerocity, ten minutes from the airport.

    Pictured: New Delhi

How and where we work

What we offer

With this role

  • A monthly model-usage budget for experiments, on approved enterprise accounts

With every role

  • Health and family

    Medical insurance · Parental leave · Mental health

  • Time

    Paid leave · Winter break · Flexible days

  • Growth

    Learning budget · Growth reviews · Internal moves

  • Setup

    Your own machine · Home office · Team weeks

The full benefits schedule

The team

Technology & Intelligence, the practice behind this role.

Engineers who build websites, platforms, data systems and AI products, with tests, evaluations and security checks on every change.

Open roles in this practice
3 on the board
Based in
Remote (India) · New Delhi · Ludhiana
Code on a screen in close-up: SVG gradient and filter definitions in pink, blue and white on a dark editor.
The practice at work Technology & Intelligence

What Technology & Intelligence delivers for clients

About Technology & Intelligence

Where this role sits

L3 of 6 · Mid

Owns a feature. Owns a piece of work from start to finish.

Each level is defined by the scope you own, not years served. Growth reviews twice a year measure you against the six standards at your level.

See career paths
  1. L1 Intern A task
  2. L2 Associate A deliverable
  3. This role L3 Mid A feature
  4. L4 Senior A workstream
  5. L5 Lead An engagement
  6. L6 Principal A practice

Level below

L2 · Associate — A deliverable. Delivers reliably, with review.

Next level

L4 · Senior — A workstream. Sets the approach and develops others.

How we hire

5 steps, and a reply after every one.

Steps set by this role’s hiring lead. Timings are targets; if one slips, we tell you.

  1. Within 5 working days

    Step 1: Application read

    An AI engineer reads it. A link to something you built and measured helps most.

  2. Week 1 · 45 min

    Step 2: Technical conversation

    An AI system you put into production: how you knew it worked and what broke.

  3. Week 2 · 2 hours, paid

    Step 3: Evaluation exercise

    Find out why a small retrieval pipeline fails ten questions, then fix what you can.

    Work sample · the brief

  4. Week 2 · 60 min

    Step 4: Design review

    Design the safety checks and approval steps for an agent that sends email on a client’s behalf.

  5. Week 3

    Step 5: Offer

    In writing, with the level, salary band and start date.

What helps an application

  • A link to work you made, with your own part in it named.
  • One project you could talk through for half an hour.
  • If you used AI, a line on how you checked what it produced.
  • Plain words are fine. We read for substance.

Adjustments. Need extra time, questions in advance, captions or another format? Tell us on the form or by email. Asking never counts against you.

Start the application

AI Engineer, Agents & RAGNew Delhi · Hybrid · Closes 30 Nov

Apply for this role

Next step

If no role fits, tell us what you would build.

Someone in the practice you choose reads your application like any other and replies either way.

Send a speculative application