Technical Lead

Nuaav; Dadri; On-site; INR 500,000 - 550,000; Full time

Job summary

Nuaav is seeking a hands-on Tech Lead with 10+ years of engineering experience (including 7+ years in data engineering) to lead a multi-track platform build on AWS. The platform is a modern data lakehouse that ingests data from diverse sources, structures it via semantic layers, and exposes it through APIs—evolving toward AI-powered capabilities.

You will own architecture and delivery end-to-end, and drive integration of LLMs and agentic AI patterns into enterprise data systems, while mentoring

Job description

We’re prioritizing Tech Leads - Data with AI exp , who have built systems & lead teams —not just explored concepts. Before you apply, a quick check — this role is hands-on and build-heavy.

If this sounds like you, we’d like to hear from you:

Have you built or led a system where LLMs interact with enterprise data (APIs, warehouses, etc.)? What was your role?

How have you designed data platforms on AWS (S3, APIs, pipelines) that serve real applications, not just analytics?

Have you worked on entity resolution / data matching problems? What approach did you use (rule-based, probabilistic, ML)?

If you were to design a natural language query layer on top of a data platform, how would you approach accuracy and reliability?

If you have clear answers to most of the above, this role is likely a strong fit.

About the Company

Nuaav is a boutique technology consulting firm focused on delivering innovative, scalable, and secure data engineering and AI solutions. We partner with corporate clients to drive impactful change through specialized expertise in product engineering, data systems, AI/ML, and user experience. Our services emphasize personalized attention, agility, and quality, enabling clients to confidently transform and grow in evolving business environments.

About the Role

We are seeking a hands-on Tech Lead with 10+ years of experience (including 7+ years in data engineering) to lead a multi-track platform build on AWS.

The platform is a modern data lakehouse that ingests data from heterogeneous sources, structures it through semantic layers, and exposes it via APIs — now evolving into an AI-powered system with natural language querying, entity resolution, and intelligent data interactions.

This role requires someone who can own architecture and delivery end-to-end, while also driving the integration of LLMs and emerging agentic AI patterns into enterprise data systems.

Key Responsibilities

• Own end-to-end architecture, design, and delivery across data, API, and AI tracks
• Design and implement scalable data ingestion pipelines (native connectors + Python-based pipelines)
• Architect and maintain lakehouse semantic layers (raw → business → application) with strong governance and lineage
• Design and build REST APIs (read/write patterns) to serve diverse consumers and applications
• Drive AI/LLM integration into the platform:
• Design data catalog / data dictionary for grounding LLM responses
• Ensure accuracy, relevance, and reliability of AI outputs
• Contribute to evolving agentic AI workflows where AI interacts with data, APIs, and tools
• Design and implement entity resolution frameworks (deterministic, probabilistic, ML-based)
• Establish best practices for CI/CD, testing, deployment, and observability across data and application layers
• Collaborate with data, product, and analytics teams to translate business problems into scalable technical solutions
• Mentor engineers, conduct code reviews, and drive engineering quality

Required Skills & Experience

• 10+ years of engineering experience with 7+ years in data engineering, including leadership responsibility
• Strong experience building on AWS (S3, Lambda, API Gateway, RDS, IAM, CodePipeline/CodeBuild, etc.)
• Deep expertise in at least one modern data platform (Databricks, Snowflake, Dremio, Trino, Iceberg, Delta, etc.)
• Strong understanding of lakehouse architectures, semantic layers, and query optimization
• Strong Python expertise for data pipelines, backend services, and automation
• Experience building and scaling REST APIs (Flask, FastAPI, or similar)
• Experience with data cataloging, metadata, and governance frameworks
• Hands‑on experience with entity resolution techniques

AI / LLM (Critical Capability)

• Experience integrating LLMs (Claude, GPT, or similar) into applications or data systems
• Understanding of RAG (Retrieval‑Augmented Generation) and grounding techniques using enterprise data
• Exposure to agentic AI concepts (multi‑step workflows, tool usage, orchestration)
• Ability to evaluate and improve LLM output quality, latency, and reliability

Preferred Skills

• Experience with Dremio (Arctic, Sonar, reflections, virtual datasets)
• Familiarity with vector databases, embeddings, or hybrid search
• Experience with open table formats (Iceberg, Delta, Parquet)
• Exposure to graph/entity resolution frameworks (Zingg, Splink, etc.)
• Knowledge of data governance tools (Collibra, Apache Atlas, etc.)
• Experience integrating BI tools (Power BI or similar)
• Experience working in consulting or multi‑workstream delivery environments

What We’re Looking For

• Engineers who can bridge data engineering and AI systems, not treat them separately
• Strong ownership mindset — from architecture to production
• Ability to work in ambiguity and evolving problem spaces
• Curiosity to explore and implement AI‑first system design patterns

Why This Role

This is not a traditional Lead - data engineering role.

You will be working at the intersection of data platforms, backend systems, and AI/LLM‑driven experiences, helping shape how enterprise systems evolve into AI‑native architectures.

Pay range and compensation package - INR 50-55 L

Early Joiners or within 30 days Joiners shall be evaluated for this role

Equal Opportunity Statement

Nuaav is committed to diversity and inclusivity in the workplace. We encourage applications from individuals of all backgrounds and experiences.