Staff GenAI Engineer

Zenskar; Bengaluru; On-site; INR 4,200,000 - 6,600,000; Full time

Job summary

Zenskar is hiring an AI-focused software engineer in Bengaluru to shape Gen AI integration across our product. You will drive reliable, cost-efficient LLM features while setting patterns others adopt, without owning every team.

This IC role demands hands-on coding on critical paths and building scalable patterns for the organization. You will design prompts, orchestration, and guardrails, ensuring outputs are trustworthy and auditable in production.

Qualifications

• 8+ years of software engineering experience with AI-powered production deployments.
• Real, shipped-at-scale systems; ML work OK if deployed to real users.
• Deep understanding of LLM application architecture and tooling.
• Experience building agentic, multi-step reasoning systems.
• Prompts treated as versioned, testable artifacts.
• Experience designing evaluation frameworks and regression pipelines.
• Strong AI observability: tracing, monitoring, feedback loops.

Responsibilities

• Turn ambiguous product asks into working LLM-based features: prompts, context design, tool calls.
• Design guardrails for hallucinations, drift, and incorrect outputs; avoid demo-grade gaps.
• Ensure no unverified truth from LLMs in financial decisions; add verification layers.
• Select models/vendors for cost, quality, latency, and data policy; optimize usage.
• Set engineering standards adopted by multiple teams without owning them.
• Build and own eval harness to catch regressions before shipping.
• Know when a deterministic approach is better than an LLM in production.
• Quantify technical debt in Gen AI systems and plan remediation.

Skills

LLM integration

Tool orchestration

Model evaluation

Cost optimization

Observability

Back-end skills

Frontend familiarity

Pattern design

Job description

Zenskar is an AI-native revenue automation platform built to handle real-world complexity.

It sits between your CRM and ERP automating everything in between: billing, revenue recognition, collections, usage metering, and analytics. Across any pricing model, any entity structure, any currency.

Our vision: Zero-Touch Finance. Agents execute. Humans supervise. Finance teams set the rules. Zenskar runs them.

Founded by Apurv Bansal and Saurabh Agarwal, second-time founders whose previous startups were acquired by Snapdeal and Gaana. The team brings experience from Google, Deutsche Bank, Elevation Capital, IIT Bombay, IIT Delhi, and Harvard Business School.

We have 5x'd revenue in the past year. We are default alive.

Funding

We raised $15M in Series A funding in April 2026, led by Susquehanna Venture Capital, Bessemer Venture Partners, Shine Capital, and Rho, with participation from Rocketship, J-Ventures, Future Back Ventures by Bain & Company, and Converge.

The funding is being used to expand our Agents Marketplace and scale operations, not headcount.

Read the announcement

About the role

This role sets the standard for how Gen AI gets built into Zenskar's product.

You're accountable for whether the Gen AI features Zenskar ships are reliable, safe, and cost-sane in production, not for whether any single feature gets built. Concretely: this role exists so that no team ever ships an LLM integration that hallucinates a wrong invoice amount, or burns unbounded API cost, because there was no standard pattern to build against.

This is an IC role with org-wide influence, not team ownership. You'll code on the critical paths where it matters most, but your leverage comes from setting patterns other teams build on top of, not from personally shipping every Gen AI feature. Think 1 to 3 year horizon for how Gen AI gets integrated across the product, not one team's roadmap.

What this role is not: foundation model training, deep RAG/retrieval specialization as a primary mandate, fine-tuning specialization, or MLOps infrastructure ownership. Those are adjacent lanes. This is LLM application engineering: building real product features on top of frontier model APIs and making them production reliable.

What you'll do

• Turn ambiguous product asks into working LLM-based features: prompt and context design, tool calling, orchestration across model calls, structured output handling
• Design for the failure modes non-deterministic systems actually have: hallucination, drift, silent wrongness. Build guardrails, and know the difference between demo-grade and production-grade because you've shipped the gap between them
• Make sure an LLM is never the unverified source of truth for a financial decision. Design the verification or human-in-loop layer wherever money is actually at stake
• Pick the right model or vendor for the job (cost, quality, latency, data policy) and avoid lock-in. Once chosen, run it efficiently: token economics, caching, batching, per-request cost tracking
• Set the technical standard other teams build their Gen AI features against, and get multiple teams to actually adopt it without having direct authority over them
• Build and own the eval harness that catches quality regressions before they ship, not ad hoc spot-checks
• Know when not to use an LLM at all, where a deterministic system would be cheaper, more reliable, or simply correct
• Name and quantify technical debt in Gen AI systems (prompt sprawl, eval gaps, untracked cost, brittle integrations) and negotiate time to address it
• Shape who joins the team by holding a technical bar in interview loops, without owning headcount decisions

What drives you

• You've seen AI systems fail in production and got obsessed with understanding why
• You think about reliability, evaluation, and observability before you think about model selection
• You believe probabilistic systems deserve the same engineering rigor as deterministic ones
• You care about systems users can trust, not systems that look impressive in a demo
• Gen AI's baseline moves monthly for you, not yearly. You actively track it: specific people, sources, releases, and can point to a real decision that changed because of a recent shift

What you'll need

• 8+ years of software engineering experience, including meaningful experience shipping AI-powered products to production
• A real, shipped-at-scale system in your track record, doesn't have to be Gen AI. If it's ML work, it shipped to real users, not fine-tuning or research that stayed in a notebook
• Deep understanding of LLM application architecture: tool use, structured outputs, retrieval, orchestration, and where these actually break in production
• Experience building agentic systems that do multi-step reasoning and interact with tools or business systems
• A track record of treating prompts as versioned, testable, deployable artifacts, not strings scattered through the codebase
• Experience designing evaluation frameworks and regression pipelines for AI systems
• Strong grasp of AI observability: tracing, monitoring, feedback loops, production debugging
• A track record of getting more than one team to adopt a pattern or standard you set, without owning those teams
• Judgment for when not to use an LLM at all
• Strong backend engineering skills, and enough frontend ability to own an AI experience end to end
• Can clearly walk through an AI system you've built two levels below the pitch: what failed, what you learned, how you improved reliability over time

Location