HamburgerMenu
hirist

Job Description

Role : Gen AI Platform Lead


Interview Mode : F2F on 16th May at Chennai


Role Summary :

The GenAI Platform Lead is responsible for architecting, building, and operating an enterprise-grade Generative AI platform that enables product teams to rapidly deliver secure, scalable, and costefficient AI-powered applications.

This role is engineering-led, combining deep backend and platform engineering expertise with applied Generative AI systems design.
It focuses on production-grade LLM integration, platform reliability, governance, and developer enablement.

Mandatory Requirements :

- 15+ years of overall IT experience, with strong expertise in :

1. Python

2. RESTful APIs

3. RDBMS

- Minimum 2+ years of hands-on experience in Generative AI / LLM-based systems, building or operating production AI platforms or services.

- Proven experience leading backend or platform engineering teams in an enterprise environment.

Hands-on exposure to LLM platforms such as :

1. Amazon Bedrock

2. Azure OpenAI

3. OpenAI

4. Anthropic

- Demonstrated ownership mindset with the ability to drive architecture, execution, governance, and operational excellence.

What This Role Is and Is Not :

This Role IS :


- AI Engineering / GenAI Platform Engineering

- Building LLM-powered backend systems

- Designing reusable GenAI platform capabilities

- Productionizing LLM workflows with governance, observability, and cost control

- Supporting multiple product teams via a shared AI platform

This Role Is NOT :


- Data Science

- ML research or experimentation

- Model training from scratch

- Statistical modeling or feature engineering

- Notebook-driven, research-focused ML workflows

Core Technical Skills :

1) Platform & Backend Engineering :

- Expert-level proficiency in Python using :

1. FastAPI

2. Django

3. Flask (or equivalent frameworks)

- Strong experience with APIfirst and platform first architecture :

1. Versioning

2. Backward compatibility

3. Lifecycle management

- Deep understanding of distributed systems, middleware design, and service integration patterns.

- Strong background in RDBMS (PostgreSQL / MySQL) :

1. Schema design and optimization

2. Complex SQL queries

3. Indexing, performance tuning, and transaction management

- Experience with ORMs (SQLAlchemy, Django ORM) and understanding of performance trade-offs.

- Solid understanding of scalability, resiliency, security, and cost optimization.

2) Generative AI & LLM Platform Expertise :

Hands-on experience integrating foundation models / LLMs via :

1. Amazon Bedrock

2. Azure OpenAI

3. OpenAI

4. Anthropic

- Experience designing reusable GenAI platform capabilities, including :

1. Prompt lifecycle management (templates, versioning, approval flows)

2. Context enrichment and grounding

3. Model routing and selection strategies

- Strong experience with RAG (Retrieval Augmented Generation) architectures :

- Vector databases such as:

1. OpenSearch / Elasticsearch

2. FAISS

3. pgvector

4. Pinecone

5. Chroma

- Embeddings, semantic search, retrieval, and ranking strategies

- Experience with LLM orchestration frameworks :

1. LangChain

2. LlamaIndex

3. Semantic Kernel (or equivalents)

Strong understanding of GenAI production constraints :

1. Token usage and cost optimization

2. Latency vs quality trade-offs

3. Caching, retries, and rate limiting


- Knowledge of AI safety and governance :

1. Hallucination mitigation

2. Prompt injection prevention

3. Output validation and policy enforcement

4. Data privacy and enterprise guardrails

Experience implementing AI observability :

1. Prompt and model traceability

2. Latency, cost, quality, and failure metrics

Cloud, DevOps & Security (Optional) :

- Experience building GenAI services on cloud platforms (AWS preferred), using services such as :

1. Lambda

2. SQS

3. Redis

4. OpenSearch / Elasticsearch

Strong understanding of :

1. CI/CD pipelines

2. Automated testing

3. Deployment and release strategies

- Familiarity with Linux, containers, and runtime troubleshooting.

- Experience collaborating with Security, CloudOps, and Governance teams.

Responsibilities :

Platform Ownership & Architecture :


- Define and own the GenAI platform reference architecture.

- Build reusable platform components enabling teams to :

1. Access LLMs securely

2. Use enterprise data safely

3. Implement guardrails and evaluations consistently


- Establish and enforce standards, best practices, and guardrails for GenAI adoption.

Engineering & Delivery Leadership :


- Lead and mentor platform engineers delivering LLM-powered services at scale.

Perform technical impact analysis considering :

1. Compute cost

2. Token usage

3. Latency

4. Scalability

5. Governance requirements

Drive high code quality via :


1. Code reviews

2. Design reviews

3. Testing discipline

- Lead large-scale refactoring and modernization efforts.

Governance, Reliability & Operations :


- Proactively manage :

1. Security vulnerabilities

2. AI risks (hallucinations, leakage, bias)

3. Platform SLAs and cost controls

- Lead root cause analysis for platform or AI-related incidents.

- Ensure continuous alignment with evolving GenAI and cloud best practices.

Nice to Have :

- Experience building internal developer platforms or AI platforms.

- Exposure to RBAC, multi-tenancy, and enterprise authorization patterns.

- Familiarity with Angular/React to align AI platform capabilities with UX.

- Experience with evaluation frameworks (offline/online evals, golden datasets).

- Exposure to enterprise compliance and audit requirements for AI systems.

info-icon

Did you find something suspicious?

Similar jobs that you might be interested in

Loading chat...