SDE 4

About us:

Portkey AI is the production stack for enterprise Generative AI teams.

In just the past year, we've grown to processing billions of LLM calls monthly for leading enterprises like Doordash, Roche, Wayground (Quizizz), and Bain.

Our platform combines an AI Gateway, Observability, Guardrails, and Prompt Governance so teams can ship AI features faster, manage costs, and meet upcoming compliance requirements.

As enterprises race to scale Gen AI across thousands of employees, Portkey is becoming the default infrastructure to make it trustworthy, efficient, and compliant.

Our Team:

We are a small but mighty team of 20 humans who are equal parts ambitious, chaotic-in-a-good-way, and obsessed with building world-class AI infra. We celebrate every small win, and genuinely root for each other.

We are growing - thoughtfully, rapidly, and with people who want to build things that make an impact.

If you want a team that's smart, kind, slightly unhinged (the good founder-led kind), and deeply committed to shaping how enterprises adopt AI…

you'll fit right in.

About the Role

We are looking for a seasoned backend engineer who can architect, build, and scale mission-critical systems powering Portkey's AI infrastructure platform. You should be comfortable owning complex distributed systems end-to-end, driving technical strategy, and raising the engineering bar while working in a fast-paced, product-focused environment.

What You'll Do

• Design and build highly scalable, low-latency backend services and APIs powering core Portkey products.
• Lead architecture for major product areas — solving hard distributed systems problems around routing, reliability, observability, performance, and data scale.
• Own system design, implementation, testing, and deployment with strong attention to reliability and correctness.
• Work closely with product, infra, and AI platform teams to deliver features with high velocity and high quality.
• Mentor engineers, influence best practices, and shape long-term technical vision.
• Drive performance optimization, cost efficiency, and operational excellence across backend systems.

What We're Looking For

• 7-10+ years of backend engineering experience with deep expertise in building large-scale distributed systems.
• Strong proficiency in Go, , Python, or similar languages, along with experience in microservices architectures.
• Expertise in both SQL and NoSQL systems (e.g., Postgres, MySQL, Redis, DynamoDB, Cassandra, etc.).
• Strong grasp of caching, queues, and event-driven architectures.
• Solid understanding of AWS/GCP, container orchestration, and modern infra/tooling.
• Experience designing and operating high-throughput, high-availability systems.
• High ownership, excellent judgment, and ability to thrive in a fast-paced environment.
• Startup or product-centric environment experience is a strong plus.

Bonus

• Experience building analytics systems at scale using ClickHouse or similar OLAP/columnar databases (Pinot, Druid, BigQuery).
• Experience building GenAI applications such as:
• Retrieval-Augmented Generation (RAG) pipelines
• AI Agents / Agentic frameworks
• Vector search systems
• Evaluation pipelines, guardrails, or LLM orchestration
• Experience with AI infrastructure, API gateways, networking layers, or observability platforms.

Critical Mindset We Look For

• Owner mentality
• treats systems end-to-end, not as isolated tasks.
• Systems thinker
• understands second-order effects and long-term maintainability.
• Bias for action
• moves fast with high quality; unblocks themselves and others.
• Pragmatic
• balances ideal architecture with product velocity.
• High bar for correctness
• Learner mindset
• stays curious, digs deep into problems, challenges assumptions.
• Collaborative