Required Software Engineer – Al Platform
What this role is really about:
You're building our AI platform. The internal system that powers AI capabilities across Product, Customer Success, Sales, Operations, Data, and IT.
This is a full-stack role where you'll own features end-to-end: design React interfaces for AI workflows, build Lambda functions that orchestrate multi-agent processes, integrate with enterprise systems (Salesforce, Workato, Snowflake), and optimize costs and performance at scale. You'll work with cutting-edge AI while building production-grade systems that handle real business operations.
If you want to build something that directly enables business growth, work across the full stack with modern tech, and have ownership over a platform that the entire company depends on, this is your opportunity.
Job responsibilities:
Build core AI platform services – Design and implement agent orchestration, prompt management, RAG, Connectors, and evaluation pipelines that power AI experiences across the company.
Develop complex agentic process – Develop a multi-step workflow that coordinates tools and services with proper observability, guardrails, and cost controls (using OpenAI Agent SDK, LangGraph, or a similar framework).
Build LLM evaluation and optimization process -Develop evaluation harnesses, offline/online experiments, prompt-testing frameworks, and dashboards to balance quality, latency, and spend across all AI services.
What this role is really about:
You're building our AI platform. The internal system that powers AI capabilities across Product, Customer Success, Sales, Operations, Data, and IT.
This is a full-stack role where you'll own features end-to-end: design React interfaces for AI workflows, build Lambda functions that orchestrate multi-agent processes, integrate with enterprise systems (Salesforce, Workato, Snowflake), and optimize costs and performance at scale. You'll work with cutting-edge AI while building production-grade systems that handle real business operations.
If you want to build something that directly enables business growth, work across the full stack with modern tech, and have ownership over a platform that the entire company depends on, this is your opportunity.
Job responsibilities:
Build core AI platform services – Design and implement agent orchestration, prompt management, RAG, Connectors, and evaluation pipelines that power AI experiences across the company.
Develop complex agentic process – Develop a multi-step workflow that coordinates tools and services with proper observability, guardrails, and cost controls (using OpenAI Agent SDK, LangGraph, or a similar framework).
Build LLM evaluation and optimization process -Develop evaluation harnesses, offline/online experiments, prompt-testing frameworks, and dashboards to balance quality, latency, and spend across all AI services.
Requirements:
5+ years of hands‑on software engineering experience building production systems at scale.
Strong proficiency in Python, with Practical knowledge of databases.
Strong grounding of LLM/AI application patterns (RAG, tool use, function calling, guardrails) and vendor APIs (OpenAI or similar).
Experience with vector store (pgvector, Pinecone, OpenSearch), feature/semantic layers, or retrieval pipelines
Familiarity with: eval frameworks, prompt/version management, offline/online A/B testing, and cost/latency optimization.
Clear written and verbal communication; able to drive alignment with concise design docs and reviews.
Nice to have:
Experience building developer platforms or internal tooling
Hands-on experience with model optimization, fine-tuning, or distillation techniques.
Deep experience with cloud infrastructure (AWS), containers (Docker, Kubernetes), and distributed systems.
Frontend development frameworks such as React.
Background in SaaS/enterprise environments with compliance requirements (SOC2, GDPR).
5+ years of hands‑on software engineering experience building production systems at scale.
Strong proficiency in Python, with Practical knowledge of databases.
Strong grounding of LLM/AI application patterns (RAG, tool use, function calling, guardrails) and vendor APIs (OpenAI or similar).
Experience with vector store (pgvector, Pinecone, OpenSearch), feature/semantic layers, or retrieval pipelines
Familiarity with: eval frameworks, prompt/version management, offline/online A/B testing, and cost/latency optimization.
Clear written and verbal communication; able to drive alignment with concise design docs and reviews.
Nice to have:
Experience building developer platforms or internal tooling
Hands-on experience with model optimization, fine-tuning, or distillation techniques.
Deep experience with cloud infrastructure (AWS), containers (Docker, Kubernetes), and distributed systems.
Frontend development frameworks such as React.
Background in SaaS/enterprise environments with compliance requirements (SOC2, GDPR).
This position is open to all candidates.
