Zenskar - Senior Generative AI Engineer

Zenskar; Bengaluru; Hybrid; INR 1,200,000 - 1,800,000; Full time

Job summary

Zenskar is looking for a Senior GenAI Engineer to own the AI layer of their product. This role involves building production AI systems integral to customer success, ensuring features are reliable and easily usable.

The ideal candidate will have 4–6 years of software development experience, with strong skills in AI feature engineering and ownership of UI design. The position is hybrid, requiring 2 days a week in the office located in Indiranagar, Bengaluru.

Qualifications

• 4–6 years of total software development experience.
• At least 1–2 years in building and shipping AI features in production.
• Can describe hard AI problems solved and what was learned.

Responsibilities

• Build the AI layer of Zenskar's product.
• Own features for enterprise clients, ensuring reliability and observability.
• Collaborate with product and engineering teams.

Skills

Software development

AI/LLM-powered features

LLM pipeline engineering

Responsible AI

Frontend skills in React

Backend engineering

Education

CS degree or equivalent

Job description

About this role

As a Senior GenAI Engineer at Zenskar, you will own the AI layer of our product – building the features that make Zenskar intelligent. This is not a research role and not a prompt‑engineering role. You will build production AI systems that enterprise clients depend on, so reliability, observability, and rigorous evaluation are as important as AI capability itself. You own the full vertical – the model, the pipeline, and the UI.

Responsibilities

• Build and own CS Copilot, a real‑time assistant for customer success teams, spanning STT pipelines, live transcription, and LLM‑powered suggestions.
• Build LLM‑powered document‑understanding features that extract structured, reliable data from unstructured enterprise documents.
• Own AI feature UIs end‑to‑end: design and implement the interface, not just the model integration layer.
• Design and maintain an evaluation framework, defining what "working" means for each AI feature and catching regressions before users do.
• Drive model selection and integration decisions, choosing the right provider and approach for each use case while managing latency and cost.
• Own AI platform reliability – observability, fallback behaviour, and graceful degradation when models fail.
• Collaborate closely with product, customer success, and full‑stack engineering to ensure AI features are usable and trusted by real users.

The Impact You'll Make

• Define what AI means at Zenskar – the features you ship will be the most visible and differentiated parts of the product.
• CS Copilot, if executed well, changes how enterprise customer success teams operate daily, creating high visibility and high impact.
• Establish the engineering culture around AI reliability at Zenskar – evaluation, observability, and disciplined iteration.
• Your work will directly accelerate enterprise deals, as AI features become an increasingly important buying criterion.
• Bring engineering rigor to a domain where most companies ship demos and call them features.

Key Qualifications

• 4–6 years of total software development experience, with at least 1–2 years actively building and shipping AI/LLM‑powered features in production.
• CS degree or equivalent – strong engineering fundamentals; this role requires a builder, not a researcher.
• Can describe hard AI problems solved, focusing on what broke, what was learned, and what changed, rather than naming models.
• LLM pipeline engineering experience – chaining, tool use, structured outputs, prompt management, and handling failure modes in production.
• Prompt lifecycle management – treat prompts as versioned, testable artifacts with a system for managing changes in production.
• RAG fundamentals – chunking strategies, retrieval quality, embedding models, and the judgment to know when RAG is the right answer.
• Evaluation discipline – has designed own evaluation sets, knows how to measure AI feature quality, and catches regressions when models change.
• Latency and cost thinking – knows when to use a smaller model, when to cache, and when streaming matters.
• Responsible AI and data privacy awareness – understands implications of passing enterprise data through third‑party models and designs pipelines accordingly.
• Product‑quality frontend skills – can own AI feature UIs end‑to‑end in React or equivalent.
• Strong backend engineering – can own the full feature without needing a backend engineer to make AI code production‑ready.

Good to Have

• Agentic systems – multi‑step agents, tool orchestration (LangGraph, CrewAI, custom), long‑running workflows.
• Voice and multimodal pipelines – STT (Deepgram, Whisper), real‑time audio processing, WebSocket streaming.
• Fine‑tuning experience – LoRA/QLoRA on open‑source models; understanding of model internals beyond the API surface.
• Open‑source model deployment – vLLM, Ollama, running models on own infrastructure.
• Enterprise AI experience – building AI for workflows where correctness and auditability matter.
• AI‑assisted development – comfortable building AI tools with AI tools; using Cursor, Copilot, or similar as a genuine force multiplier.
• Experience with financial systems, billing platforms, or fintech applications.
• Knowledge of SaaS business models and compliance frameworks.
• API design and integration experience.
• Prior experience working at a startup.
• Not taking yourself too seriously.

What Drives You

• Been embarrassed by an AI feature failing in production – fixed it systematically, not with a workaround.
• Think about evaluation before model choice – reliability is the product.
• Apply the same engineering rigor to probabilistic systems as to deterministic ones.
• Own AI features end‑to‑end – the model, the pipeline, the UI, and fallback behaviour.
• Find it unsatisfying to ship a demo – want to ship something that holds up under real enterprise usage.
• AI landscape changes weekly – energized, not exhausted; genuinely curious and stay ahead of it.

Location

• Hybrid: 2 days per week.
• Office location: Indiranagar, Bengaluru.
• Address: 3rd Floor, A wing No 1, Carlton Towers, HAL Old Airport Rd, HAL 2nd Stage, Indiranagar, Bengaluru, Karnataka 560008.