Lead AI Engineer (Agentic Systems, Pharma domain)

TalentXO

Bengaluru

Hybrid

INR 4,000,000 - 7,000,000

Full time

5 hours ago

Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Hybrid work flexibility

Immediate joiner

Job summary

TalentXO Bengaluru-based lead AI engineer role focusing on architecting agentic pipelines for pharma data platforms. You will own subsystem designs, build production RAG pipelines, and ensure regulatory compliance (GxP, 21 CFR Part 11) while driving observability and CI/CD.

Immediate joiner preferred in a hybrid setup with in-office collaboration. Role requires hands-on experience with multiple agentic frameworks, Python excellence, and cloud/deployment skills across AWS/Azure/GCP.

Qualifications

6+ years of software or ML engineering with recent 2+ years shipping production LLM/agentic AI in pharma domain.
Hands-on proficiency with at least two agentic frameworks (LangGraph, LangChain, AutoGen, CrewAI) and debugging internals.
Direct SDK experience with Claude/OpenAI/Vertex AI and tools API usage.
Expert Python with production-quality code, typing, tests, packaging, and profiling.
RAG pipeline depth with embedding models, vector stores, and evaluation harnesses.
Cloud deployment with AWS/Azure/GCP; Docker, Kubernetes, IaC (Terraform/CDK); CI/CD pipelines.
Agent observability experience (LangSmith, Helicone) for latency, cost, quality diagnostics.
Hybrid work capability; immediate joiner; role is hybrid with limited WFH.

Responsibilities

Design and implement complex agentic pipeline components and topology.
Own subsystem designs: data flows, API contracts, and failure handling.
Lead production RAG pipelines: ingestion, chunking, embeddings, search, latency tuning.
Integrate pharma data platforms via REST / event-driven patterns.
Own observability and evaluation harnesses for components.
Lead CI/CD for modules: containerisation, tests, staging gates, rollbacks.
Translate pharma analytics demands into component specs.
Ensure 21 CFR Part 11, HIPAA, and GxP traceability in designs.
Develop document processing pipelines for pharma content.
KOL mapping, competitive intelligence, signal detection agents.
Act as technical reference for AI Engineers; review design & unblock issues.
Run design reviews and surface architecture risks pre-staging.
Mentor juniors and document patterns in knowledge base.
Represent engineering quality in client discussions; translate trade-offs clearly.
Contribute guardrail templates to internal AI playbook.

Skills

Agentic systems architecture

Python

Production LLM / agentic AI

Frameworks: LangGraph / LangChain / @

Debugging framework internals

Docker / Kubernetes

CI/CD pipelines

Observability (LangSmith / Helicone)

Regulated pharma data handling

Component design specifications

Hybrid work / immediate joiner

Tools

LangGraph

LangChain

AutoGen

CrewAI

Pinecone

Weaviate

pgvector

AWS

Azure

GCP

Terraform

CDK

Docker

Kubernetes

LangSmith

Helicone

IQVIA / Symphony / Veeva integrations

Job description

Design and implement complex components of agentic pipelines — multi-agent graphs, tool orchestration layers, retrieval modules, and memory systems — using LangGraph, AutoGen, CrewAI, or equivalent

Take ownership of full sub-system designs: define agent topology, data flows, API contracts, and failure handling for a bounded scope

Build and optimise production RAG pipelines: document ingestion, chunking strategy, embedding selection, hybrid search, retrieval evaluation, and latency tuning

Integrate agentic systems with pharma data platforms (IQVIA, Symphony, Komodo, Veeva) via REST, event-driven hooks, and batch pipeline patterns

Own observability for components: instrument trace logging, cost metrics, drift alerts, and evaluation harnesses using LangSmith, Helicone, or equivalent

Lead CI/CD for owned modules: containerisation (Docker/Kubernetes), automated test suites, staging gate criteria, and rollback procedures

Translate medical affairs, commercial analytics, and clinical ops requirements into agent component specifications

Apply 21 CFR Part 11 auditability, HIPAA-compatible data handling, and GxP traceability patterns to every component

Build intelligent document processing pipelines for pharma content: drug labels, clinical study reports, HEOR dossiers, and regulatory submissions

Contribute to KOL mapping, competitive intelligence, and signal detection agents with domain-aware retrieval and reasoning strategies

Serve as the day-to-day technical reference for AI Engineers on the pod: code review, design feedback, unblocking implementation issues

Lead component-level design reviews and surface architecture risks before they reach staging

Pair with junior engineers on hard problems and document patterns and decisions in the team's shared knowledge base

Represent engineering quality in client-facing technical discussions and translate complex trade-offs into plain language

Contribute reference implementations and guardrail templates to the firm's internal agentic AI playbook

Role is based in Bengaluru

Immediate joiner required — must be able to start within the next week

Role is within pharmaceutical and life sciences industry context

Roles & Responsibilities

Design and implement complex components of agentic pipelines — multi-agent graphs, tool orchestration layers, retrieval modules, and memory systems — using LangGraph, AutoGen, CrewAI, or equivalent
Take ownership of full sub-system designs: define agent topology, data flows, API contracts, and failure handling for a bounded scope
Build and optimise production RAG pipelines: document ingestion, chunking strategy, embedding selection, hybrid search, retrieval evaluation, and latency tuning
Integrate agentic systems with pharma data platforms (IQVIA, Symphony, Komodo, Veeva) via REST, event-driven hooks, and batch pipeline patterns
Own observability for components: instrument trace logging, cost metrics, drift alerts, and evaluation harnesses using LangSmith, Helicone, or equivalent
Lead CI/CD for owned modules: containerisation (Docker/Kubernetes), automated test suites, staging gate criteria, and rollback procedures
Translate medical affairs, commercial analytics, and clinical ops requirements into agent component specifications
Apply 21 CFR Part 11 auditability, HIPAA-compatible data handling, and GxP traceability patterns to every component
Build intelligent document processing pipelines for pharma content: drug labels, clinical study reports, HEOR dossiers, and regulatory submissions
Contribute to KOL mapping, competitive intelligence, and signal detection agents with domain-aware retrieval and reasoning strategies
Serve as the day-to-day technical reference for AI Engineers on the pod: code review, design feedback, unblocking implementation issues
Lead component-level design reviews and surface architecture risks before they reach staging
Pair with junior engineers on hard problems and document patterns and decisions in the team's shared knowledge base
Represent engineering quality in client-facing technical discussions and translate complex trade-offs into plain language
Contribute reference implementations and guardrail templates to the firm's internal agentic AI playbook
Role is based in Bengaluru
Immediate joiner required — must be able to start within the next week
Role is within pharmaceutical and life sciences industry context

Requirements

Strong Lead AI Engineer Profile with agentic systems architecture expertise and pharma regulated-environment experience
Mandatory (Experience 1): Must have 6+ years of software or ML engineering, with at least recent 2+ years building and shipping production LLM or agentic AI systems in pharma domain
Mandatory (Tech skill 1): Must have hands‑on proficiency with at least two agentic frameworks (LangGraph, LangChain, AutoGen, CrewAI), with experience debugging framework internals
Mandatory (Tech skill 2): Must have direct SDK experience with Anthropic Claude API (tool use, streaming), OpenAI Assistants API, or Vertex AI Agent Builder
Mandatory (Tech skill 3): Must have Python mastery — production‑quality code, type annotations, unit and integration tests, packaging, and performance profiling
Mandatory (Tech skill 4): Must have RAG pipeline depth — embedding model selection, vector stores (Pinecone, Weaviate, pgvector), hybrid retrieval, RAGAS or custom evaluation harnesses
Mandatory (Tech skill 5): Must have cloud deployment experience with AWS, Azure, or GCP; Docker, Kubernetes, IaC basics (Terraform or CDK), and CI/CD pipelines
Mandatory (Tech skill 6): Must have agent observability experience — LangSmith, Helicone, or equivalent — with ability to diagnose latency, cost, and quality issues in production traces
Mandatory (Tech skill 8) : Must have owned full sub‑system designs — agent topology, data flows, API contracts, failure handling — for a bounded scope, and built multi‑agent graphs, tool orchestration, retrieval, and memory systems.
Mandatory (Tech skill 7): Must have track record of shipping 2+ agentic or ML systems to production — not just proof‑of‑concepts — with documented performance benchmarks
Mandatory (Domain 1): Must have working knowledge of pharma commercial data (Rx/claims, NPI‑level analytics, brand performance metrics) and experience operating in regulated data environments (GxP, 21 CFR Part 11, HIPAA‑compliant data handling)
Mandatory (Domain 2): Must have exposure to at least one of: medical affairs analytics, RWE, clinical operations data, HEOR/market access, or regulatory intelligence
Mandatory (Communication): Must be able to write crisp component specifications and communicate architectural trade‑offs to both engineers and non‑technical stakeholders
Mandatory (Availability): Must be an immediate joiner or currently serving notice period, able to start within the next week
Mandatory (Note 1) : Role is Hybrid, WFH flexibility as well upto 6 days a month
Mandatory (Note 2): CTC is inclusive of 10% variable
Preferred (Tech skill 1): MCP (Model Context Protocol); Veeva Vault, Medidata, IQVIA, or Symphony Health integrations; knowledge graphs (Neo4j, Amazon Neptune); RLHF/fine‑tuning/model adaptation; prior consulting / services‑firm delivery experience