Lead AI Engineer

About US:-

We turn customer challenges into growth opportunities.

Material is a global strategy partner to the world’s most recognizable brands and innovative companies. Our people around the globe thrive by helping organizations design and deliver rewarding customer experiences.

We use deep human insights, design innovation and data to create experiences powered by modern technology. Our approaches speed engagement and growth for the companies we work with and transform relationships between businesses and the people they serve.

Srijan, a Material company, is a renowned global digital engineering firm with a reputation for solving complex technology problems using their deep technology expertise and leveraging strategic partnerships with top-tier technology partners. Be a part of an Awesome Tribe

Role: Lead Agentic AI Engineer

Experience: 5–10 years

Employment Type: Full-time

ROLE SUMMARY

We are looking for a Lead Agentic AI Engineer who can own the end-to-end design and delivery of complex, production-grade agentic systems. You will be the go-to technical expert and the engine room of our most demanding AI initiatives — turning ambiguous client challenges into scalable, functional platforms. You will drive technical solutioning for client engagements, architect multi-agent pipelines, and bridge AI engineering with business outcomes while elevating the capability of the team around you.

WHAT YOU'LL DO

Agentic Architecture & Engineering

System Design: Architect multi-agent systems — orchestrator/sub-agent patterns, state machines, tool registries — using Microsoft Agent Framework, LangGraph, CrewAI, AutoGen, or Semantic Kernel

Advanced RAG: Design and optimize retrieval pipelines: hybrid search, re-ranking, query expansion, multi-hop reasoning, and knowledge graphs

Model Adaptation: Apply Quantization, PEFT/LoRA fine-tuning, and prompt optimization techniques to adapt foundation models for client-specific tasks

Guardrails & Hallucination Control: Design and enforce comprehensive guardrail frameworks — output validation, factual grounding checks, prompt injection defenses, content filtering, and hallucination-mitigation strategies (chain-of-verification, retrieval grounding, self-consistency) — for enterprise-grade deployments

MLOps & Production Readiness

Deployment: Productionize AI services on AWS / Azure using Docker, Kubernetes, and CI/CD pipelines (GitHub Actions / Azure DevOps)

Observability: Build comprehensive monitoring for LLM systems — tracking accuracy, hallucinations, latency, cost, and drift using LangSmith or Arize Phoenix

Evaluation: Define and implement LLM evaluation suites using RAGAS, G-Eval, TruLens, or custom metrics aligned to client KPIs

Cost & Token Optimization: Drive down inference costs through token budgeting, prompt compression, KV-cache management, model routing, streaming strategies, and intelligent batching — balancing performance against cost at scale

CI/CD: Own and evolve CI/CD pipelines for ML systems, enforcing automated testing (unit, contract, and model-quality tests) as a standard across all engagements

Performance Tuning: Optimize model serving for high-throughput production using vLLM, DeepSpeed, or Triton Inference Server

Client Solutioning & Leadership

Solutioning: Lead technical discovery and proposal for AI engagements; translate ambiguous client problems into actionable AI solutions

Mentorship: Guide junior engineers, review architecture decisions, and build the team’s internal library of reusable AI patterns, accelerators, and playbooks

Stakeholder Communication: Present solution designs, demo prototypes, and communicate technical trade-offs clearly to client technical and business stakeholders

MUST-HAVE QUALIFICATIONS

Experience: 5–10 years in software engineering or data science, with at least 3 years in applied Gen AI / LLM engineering in a services or consulting context

Agentic Frameworks: Proven experience building production agents with LangGraph, CrewAI, AutoGen, or Semantic Kernel

RAG & Retrieval: Deep expertise in RAG architectures, vector databases (Pinecone, Qdrant, Weaviate), and embedding pipelines

LLMs: Strong working knowledge of GPT-4o, Claude 3.x/4.x, Gemini, and open-source models (Llama 3, Mistral)

Cloud & DevOps: Hands-on with AWS / Azure AI services; Docker, Kubernetes, and CI/CD workflows

Engineering: Strong Python, FastAPI, SQL; software design patterns; a “software engineering first” approach to ML — with rigorous unit, integration, and model-quality testing

MLOps & Productionization: Proven track record taking LLM systems from prototype to production — owning deployment pipelines, observability, evaluation suites, guardrails, and ongoing model health in live client environments

Education: B.Tech / B.E. / M.Tech in Computer Science or related discipline

GOOD TO HAVE

Fine-tuning: Experience with PEFT/LoRA fine-tuning workflows and serving optimized models

Performance Tuning: Hands-on experience with vLLM, DeepSpeed, or Triton Inference Server for high-throughput model serving

Knowledge Graphs: Exposure to GraphRAG or ontology-based retrieval strategies

Multi-modal: Experience with vision-language models or multi-modal agent pipelines

Certifications: AWS Solutions Architect, Azure AI Engineer Associate, or equivalent

Originally posted on Himalayas