Generative AI/ Document Intelligence Engineer

Tata Consultancy Services; Bengaluru; On-site; INR 1,800,000 - 2,300,000; Full time

Job summary

Tata Consultancy Services Bengaluru is seeking a senior AI Platform Engineer to design end-to-end GenAI systems, including LLMs, RAG pipelines, embeddings, and semantic search.

You will build scalable document pipelines, integrate OCR and document intelligence, and optimize for accuracy, cost, and explainability while enforcing security and governance. The role requires deep Python expertise, AWS experience, and production-ready AI solutions.

Qualifications

• Hands-on experience building GenAI solutions and LLMs
• Experience with OCR and document intelligence across unstructured data
• Strong understanding of NLP concepts (entity extraction, classification)
• Experience with multiagent architectures and workflows
• Ability to fine-tune models for accuracy and explainability
• Design end-to-end AI platforms and large-scale document pipelines
• Knowledge of RAG vs alternative architectures and hybrid search
• Experience with serverless patterns for scalable processing
• Awareness of token usage, OCR costs, and scaling drivers
• Strong Python development skills and AI/ML ecosystems

Skills

GenAI Solutions

OCR & Document Intelligence

NLP Concepts

Agentic Architectures

Explainability

AI Platform Design

RAG Architectures

Serverless Patterns

Cost vs Scale

Python Development

Cross-functional Collaboration

Prompt Engineering

Model Orchestration

Security & Compliance

Tools

AWS (Preferred)

S3

Lambda

Terraform

Job description

Key Skills:

1) Core AI & ML Skills:

• Hands-on experience building GenAI solutions (LLMs, RAG pipelines, embeddings, semantic search)
• Practical use of OCR and document intelligence techniques across unstructured data (PDFs, images, scanned forms)
• Strong understanding of NLP concepts (entity extraction, classification, keyword detection)
• Experience with agentic / multiagent architectures and workflow-based AI systems
• Ability to adapt or fine-tune models for accuracy, confidence scoring, and explainability

2) Architecture & System Design:

• Proven ability to design end-to-end AI platforms, beyond proof-of-concepts
• Experience with large-scale document pipelines (ingestion processing indexing retrieval)
• Strong knowledge of RAG vs alternative architectures (hybrid search, knowledge graphs, semantic indexing)
• Experience with event-driven and serverless patterns for scalable processing
• Ability to reason about trade-offs (accuracy vs cost, latency vs scale, complexity vs maintainability)

3) Cloud & Platform Engineering:

• Strong experience in at least one major cloud platform (AWS preferred)
• Familiarity with:
• Object storage (e.g. S3)
• Serverless compute (e.g. Lambda)
• Managed AI/ML and OCR services
• Infrastructure-as-Code mindset (e.g. Terraform or equivalent)
• Ability to design cloud-agnostic solutions where required

4) AIAugmented Engineering (Prompt Coding & AI Pairing):

• Strong ability to use prompt engineering / prompt coding to generate, debug, and accelerate production-quality code
• Demonstrated capability to pair-program effectively with AI tools, iterating prompts and validating outputs
• Ability to apply judgement on when to rely on vs avoid AI-generated code, especially for security or critical logic
• Experience integrating AI into engineering workflows (test generation, documentation, code reviews)
• Maintains strong engineering fundamentals and code quality standards while leveraging AI as a productivity multiplier

5) MCP AI Integration (Model, Context, Platform Integration):

• Experience integrating AI models into enterprise systems using API-first and service-oriented architectures
• Ability to design model orchestration layers that connect LLMs, tools, data sources, and workflows (e.g. retrieval systems, APIs, event streams)
• Strong understanding of context injection patterns (prompt construction, metadata enrichment, grounding, tool usage)
• Experience building scalable integration pipelines between AI services and enterprise platforms (e.g. ECM systems, data lakes, APIs)
• Awareness of security, governance, and compliance controls in AI integration (PII handling, access control, audit logging, isolation boundaries)

6) Production Readiness & Operations:

• Clear understanding of production-ready AI systems, including:
• Monitoring and alerting
• Reliability and resilience
• Scalability and performance
• Observability and runtime support
• Experience integrating into CI/CD and DevSecOps pipelines
• Awareness of security scanning, vulnerability management, and secure deployments

7) Responsible AI & Risk Awareness:

• Strong grounding in responsible AI principles, including:
• Governance and auditability
• Explainability and transparency
• Bias and fairness considerations
• Human-in-the-loop controls
• Experience working in regulated or high-risk environments
• Ability to design solutions with compliance and audit requirements in mind

8) Cost & Performance Optimization:

• Ability to design for cost-efficient AI usage, including:
• Model selection and tiering
• Caching and reuse strategies
• Routing tasks to appropriate model complexity
• Awareness of token usage, OCR costs, and scaling cost drivers
• Experience implementing logging, metrics, and cost observability

9) Engineering & Delivery Skills:

• Strong Python development skills and familiarity with AI/ML ecosystems
• Ability to deliver end-to-end solutions (POC MVP production)
• Experience working in cross-functional engineering teams
• Comfortable operating as a senior individual contributor with architectural influence

10) Communication & Collaboration:

• Ability to explain complex AI systems to technical and non-technical stakeholders
• Comfortable collaborating with platform, security, and compliance teams
• Balances hands-on delivery with design leadership