Home/Jobs/Lead AI Engineer

Lead AI Engineer

Bridge-it

Delhi

4-8 years

Today

$34.9K–55.4K/yr

Full-time

Remote

Skills Required LLM

RAG

LangChain

OpenAI

Gemini vLLM

LangGraph

OpenRouter

Milvus pgvector

Neo4j

Cypher

Cohere

LangSmith

OpenTelemetry

Description Bridge-it is an early-stage EdTech company building a career-readiness platform for K-12 students, counselors, and districts. The role leads the AI Copilot team and owns agentic workflows, retrieval, safety, evaluation, and production reliability.

Company: Bridge-it

Role: Lead AI Engineer

Location: Remote | New Delhi, Delhi, India

Experience

- 4–8 years in industry
- 4–8 years of professional software engineering experience
- 2–5 years building LLM-powered products in production
- 2 years of leading a team
- Solid Python engineering fundamentals
- Strong grasp of agentic architecture patterns
- Hands-on experience with agent orchestration frameworks
- Context engineering / harness engineering experience
- Experience designing and optimizing agent memory
- Deep practical knowledge of RAG systems
- Proven experience building and operating LLM evaluation systems
- Hands-on AI observability experience
- Experience shipping structured outputs as product interfaces
- Comfort with cloud infrastructure
- Excellent communication and interpersonal skills
- Demonstrated ability in requirement analysis and task decomposition

Responsibilities

- Design, build, and operate agentic LLM workflows in LangGraph serving live student and counselor traffic over WebSockets
- Own RAG quality across vector stores, knowledge graph, and structured platform data
- Build chunking strategy, reranking, and grounded generation with typed claims and evidence citation
- Enforce safety and trust with guardrails, constitutional rules, faithfulness verification, abstain/escalate behavior, and tenant isolation
- Build and extend the evaluation platform with online evaluators,



offline regression suites, latency baselines, and A/B experimentation
- Drive latency and cost optimization across model selection, prompt and context engineering, selective retrieval, caching, and streaming
- Instrument and debug production behavior using tracing and observability tools
- Partner with backend, frontend, and product teams on response envelopes, interaction contracts, and rollout plans
- Break epics into staged implementation plans with acceptance criteria
- Sequence work across engineers, review code, and mentor teammates
- Analyze ambiguous product requirements and turn them into well-scoped technical specs and tickets
- Communicate trade-offs clearly to product and leadership

Additional Responsibilities

- Lead the AI Copilot end to end
- Own the agentic orchestration graph
- Own retrieval and grounding
- Own safety guardrails
- Own response contracts with the frontend
- Own the evaluation platform that keeps the system honest
- Contribute to the redesign that collapses multiple experimental graph variants into a single workflow-first architecture
- Introduce typed claim verification, constitutional rules, and per-turn decision records
- Treat live-QA findings as first-class inputs to design
- Grow into a techno-management position

Nice To Have

- Experience at an early-stage startup
- Working knowledge of MCP
- Knowledge graphs in retrieval or recommendation contexts
- Durable workflow engines and event-driven architectures
- Multi-tenant SaaS security models
- FERPA/COPPA-adjacent compliance awareness




- EdTech or other regulated/high-trust consumer domains
- AI infrastructure experience
- Model serving experience
- GPU inference experience
- Gateway/router layers
- Cost/latency-aware routing across providers
- SLMs and self-hosted LLMs
- vLLM
- TGI
- Ollama
- Quantization
- Fine-tuning
- Distillation
- Traditional ML
- scikit-learn
- PyTorch
- Recommender systems
- Forecasting and data analytics
- Time-series methods
- Cohort analysis
- Product analytics
- Big data processing/streaming
- Spark
- Flink
- Kafka
- dbt-style transformation workflows

More Skills Python, agentic workflows, routing, planning, parallel retrieval, tool execution, verification, streaming, chunking, reranking, typed claims, evidence citation, input/output guardrails, constitutional rules, faithfulness verification, multi-tenant data isolation, LLM-as-judge evaluators, New Relic, Sentry, PostHog, JSON contracts, schema validation, GCP, Cloud Run, Pub/Sub, GCS, BigQuery, Django, PostgreSQL, Next.js, WebSockets, Temporal, MCP, OpenTelemetry GenAI, Open-weight models

Prepare for this role

Recommended resources to build the skills for this position. Sponsored.

Top 20 LLM System Design Questions (Quick)

Zenaique A focused LLM system design interview question set.

Top 50 LLM System Design Interview Questions

Zenaique

Curated LLM system design questions from Zenaique.

Top 50 LangChain Interview Questions

Zenaique

Curated LangChain interview questions covering chains, agents, and memory.

More LLM jobs

Senior Software Engineer -AI

Thomson Reuters

Bengalore

Today

AI/ML Data Science / Gen AI

Cognizant

Chennai

Today

Lead I - ML Engineering

UST

Thiruvananthapuram

Today

AI Engineer

Cornerstone

Hyderabad

Today

Senior Applied AI Engineer

Conqr AI

India

Today

Senior AI Engineer - Manager

Vialto

Bengalore

Today

📌 Lead AI Engineer (Delhi)
🏢 Top Gen AI Jobs
📍 Delhi