11 days ago
Pune, IndiaSenior
Responsibilities
- Build and integrate AI-driven features using LLM APIs from OpenAI, Azure OpenAI, Anthropic, and Gemini on Vertex AI.
- Design tool-using and multi-agent workflows with structured function calling, schema validation, planning, memory/state, retries, fallbacks, and safe tool execution.
- Develop document understanding, extraction, evidence reasoning, task automation, and multi-step decision-support workflows.
- Implement context engineering, retrieval strategies, grounding, context budgeting, compression, and retrieval-augmented generation workflows.
- Establish evaluation frameworks with golden datasets, adversarial cases, regression tests, rubric-based scoring, automated pipelines, release gates, and online metrics.
- Develop scalable backend services and APIs and integrate AI pipelines into cloud, microservices, and event-driven architectures.
- Implement observability, tracing, prompt versioning, evaluation tracking, cost monitoring, reliability, performance, security, guardrails, and fallback logic.
- Build internal tools for evaluation, testing, prompt and version management, and safe deployment.
- Partner with product managers, designers, the Chief Architect, and domain subject-matter experts to prototype and refine AI-first solutions.
- Document system behavior, failure modes, and operational playbooks while following compliance, privacy, and responsible AI guidelines.
Requirements
- Strong software engineering background with Python preferred and experience shipping backend services.
- Deep hands-on experience building agentic LLM systems from first principles, including agent loops, tool interfaces, planning or replanning, memory or state, and failure handling.
- Strong context engineering experience covering retrieval, routing, grounding, context budgeting, and long-context tradeoffs.
- Strong evaluation discipline involving golden datasets, regression gating, automated evaluation pipelines, and online monitoring.
- Practical experience with LLM APIs such as OpenAI, Azure OpenAI, Anthropic, or Gemini and AI orchestration frameworks.
- Experience shipping an LLM or agent system in production and explaining failure modes, evaluation methods, cost and latency improvements, and safe monitoring and iteration.
- Strong debugging, systems thinking, problem decomposition, ownership, and ability to work in fast-paced ambiguous environments.
- Preferred experience with AWS or GCP, microservices, event-driven systems, OpenTelemetry, Datadog, Honeycomb, Langfuse, Braintrust, HumanLoop, MLFlow, Temporal, Celery, or Airflow.
- Preferred experience building enterprise AI features involving permissions, auditability, compliance constraints, PII handling, prompt-injection defenses, or sandboxed tool execution.
Benefits
- Health coverage for employees and immediate family members.
- Flexible paid time off and 10 company-paid holidays annually.
- Paid leave for birth parents, non-birth parents, and caregivers, plus surrogacy and adoption reimbursement.
- Employer-paid life and disability insurance.
- Voluntary hospital indemnity, critical illness, and accident coverage.
- Flexi and NPS tax-advantaged accounts.
- One paid volunteer day each year.
- Competitive compensation and opportunities for rapid advancement.
Tech Stack
Categories
About Onit
Onit builds enterprise legal operations software used by corporate legal departments and law firms to manage contracts, matters, e‑billing, legal holds, and related workflows. Its products are delivered as SaaS with implementation and integration services, emphasizing process automation and AI‑assisted review and approval. The company is privately held, headquartered in Atlanta, Georgia, and operates globally with additional offices worldwide.