4 days ago
Bengaluru, IndiaStaff+
Responsibilities
- Architect and build the Agentic Harness for complex, multi-step AI workflows across models, tools, data, and services.
- Design interfaces for tool execution, context, state, memory, permissions, retries, fallbacks, and human review.
- Build evaluation harnesses, datasets, automated graders, experiment pipelines, release gates, simulations, replay infrastructure, and production measurements.
- Analyze agent trajectories and incidents to identify failure modes, perform root-cause analysis, and prevent regressions.
- Improve agent efficiency through model routing, prompt and semantic caching, context compaction, tool-result management, and token optimization.
- Productionize secure, observable, multi-tenant model capabilities and define evaluation standards across multiple teams.
- Set technical direction, lead cross-team projects, mentor engineers, and remain hands-on with implementation and debugging.
Requirements
- 9+ years of software engineering experience, including technical leadership of complex production systems.
- Direct experience shipping and operating LLM applications, AI agents, or model-backed workflows in production.
- Strong background in distributed systems, service architecture, high-throughput APIs, concurrency, and failure handling.
- Experience building an agent runtime, workflow engine, developer platform, evaluation system, or similar infrastructure.
- Experience evaluating nondeterministic systems, production observability, structured traces, replay, metrics, logs, and incident diagnosis.
- Fluency in Python and strong proficiency in at least one of Java, Go, Rust, or TypeScript.
- Hands-on knowledge of tool calling, structured generation, retrieval, context engineering, prompt management, and model APIs.
- Ability to balance agent quality with latency, reliability, security, and inference cost, and to set technical direction across organizational boundaries.
- Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
- Preferred experience includes human-evaluation programs, multi-agent orchestration, simulations, adversarial testing, retrieval systems, multi-tenant sensitive-data systems, model training or fine-tuning, databases, SQL engines, data platforms, Kubernetes, or cloud-native infrastructure.
Tech Stack
Categories
About Snowflake
Snowflake builds a cloud-native data platform used by enterprises to store, integrate, share, and analyze data across AWS, Azure, and Google Cloud. Its core products span data warehousing, data lakes, data engineering, and governed data sharing, sold via consumption-based subscriptions. Founded in 2012 and publicly traded on the NYSE (SNOW) following a 2020 IPO, Snowflake supports analytics and data application workloads across industries.