Get to know us better

CodiLime is a software and network engineering industry expert and the first-choice service partner for top global networking hardware providers, software providers and telecoms. We create proofs-of-concept, help our clients build new products, nurture existing ones and provide services in production environments. Our clients include both tech startups and big players in various industries and geographic locations (US, Japan, Israel, Europe).

While no longer a startup - we have 250+ people on board and have been operating since 2011 we’ve kept our people-oriented culture. Our values are simple:

• Act to deliver.

• Disrupt to grow.

• Team up to win.

The project and the team

You will work on a large-scale, multi-tenant B2B commercial execution platform used by enterprise go-to-market teams. It combines cloud software, capability benchmarking and advanced analytics to turn commercial strategy into measurable action - from account planning and partner management to pricing and sales performance.

This is a backend-focused Software Engineering role with a strong AI component. You'll build and operate the Python services behind the platform - APIs, data access, background processing - and you'll design and integrate the generative AI capabilities that sit on top of them: connecting LLMs with the platform's enterprise data, APIs and internal tools through prompt design, tool calling, workflow orchestration, guardrails and human review, all instrumented so that quality, latency and cost are measurable rather than assumed.

Daily use of AI development tools is part of how the whole team works, not an add-on. You're expected to use assistants like Claude Code across coding, testing, debugging and code review - and to validate everything they produce before it reaches production.

You'll be in regular, direct contact with product managers, designers and client-facing stakeholders, and you'll collaborate with a dedicated team of data scientists on the platform's harder analytical challenges: you own the product integration layer, they own the deeper modelling work. Security runs through everything. This is a multi-tenant SaaS platform handling sensitive enterprise client data, so every service you ship needs to respect tenant isolation, role-based access control and least-privilege data access - across the API, data and AI workflow layers.

Technology stack:

• Backend: Python, FastAPI, Pydantic, REST, pytest

• Data: SQL, PostgreSQL, SQLAlchemy/async drivers, Snowflake, Redis

• Cloud & DevOps: Azure / AWS, Docker, Kubernetes, GitHub Actions

• AI: LLM APIs, prompt engineering, tool/function calling, LangChain/LangGraph, RAG, vector search (pgvector, Pinecone)

• AI-assisted Development: Claude Code, Codex

• AI observability & MLOps: LangSmith, Langfuse, Arize Phoenix, OpenTelemetry

• Authentication & Security: OAuth 2.0, Okta, JWT, RBAC

• Real-Time & Messaging: Temporal, Socket.IO / WebSockets

What else you should know:

• Team: Product Managers, UX Designers, Fullstack Engineers, Data Engineers, DevOps Engineers, AI Engineers, Data Scientists

• You own the product-facing AI integration layer; deeper ML and data-science work is handled by dedicated specialists you collaborate with

• AI-augmented development is a core expectation of the role, not optional - daily use of tools like Claude Code or Codex across coding, testing, debugging, and code review

• Multi-tenant SaaS platform handling sensitive enterprise client data - a security-first mindset is expected at every layer

• Agile, collaborative, impact-driven environment with close cooperation with business and client-facing stakeholders

• Strong ownership culture and product mindset

We work on multiple interesting projects at a time, so it may happen that we’ll invite you to an interview for another project if we see that your competencies and profile are well suited for it.

Your role

As a part of the project team, you will be responsible for:

• Designing, building, testing and operating production Python services with FastAPI - endpoint design, data validation with Pydantic, auth, error handling and observability

• Writing and optimizing SQL against PostgreSQL and contributing to schema and data-model decisions

• Deploying and running services on Kubernetes, including reasoning about stateful vs stateless workloads and what that means for databases and persistent data

• Building and integrating generative AI features that connect LLMs with the platform's enterprise data, APIs and internal tools - prompt design, tool calling, workflow orchestration, context management, guardrails and human review

• Evaluating AI workflows and monitoring quality, latency, cost, and failure rates

• Maintaining a solid automated test suite (pytest) and helping build automated quality gates

• Using AI coding assistants effectively while validating all generated output before it reaches production

• Applying security-first thinking at every layer, including tenant isolation, role-based access control, and least-privilege data access across UI, API, and AI workflows

• Participating in code reviews, identifying architectural and AI-reliability risks, and improving engineering practices

• Documenting data flows, API contracts and AI workflow behaviour clearly enough for non-engineers to act on

Do we have a match?

As an AI Engineer, you must meet the following criteria:

• 6+ years of professional experience in software engineering with Python

• Experience with FastAPI and Pydantic - endpoint design, dependency injection, models and validators, auth and error handling

• Solid REST API design - versioning, predictable error semantics, token management, retries - with OAuth 2.0/Okta, JWT and role-based access control (RBAC)

• Experience with automated testing with pytest

• Strong SQL fundamentals (joins, GROUP BY, aggregate functions, query optimisation) and hands-on experience using PostgreSQL from Python - ORMs, database drivers, and a clear understanding of the trade-offs between synchronous and asynchronous drivers

• Solid experience deploying and operating applications on Kubernetes

• Experience with CI/CD pipelines (ideally GitHub Actions)

• Hands-on experience integrating LLM APIs into production applications, including prompt design, tool/function calling, and safe handling of non-deterministic output

• Experience using AI coding assistants such as Claude Code, Codex, or similar on a daily basis

• Understanding of multi-tenant SaaS application security

• Ability to evaluate AI features and monitor quality, latency, cost, and reliability

• Product mindset and ownership - you identify problems, propose solutions, and take features from idea to production

• Strong communication skills and good knowledge of English (minimum C1 level)

Beyond the criteria above, we would appreciate the following nice-to-haves:

• Evaluation and observability tooling for LLM features: eval harnesses, tracing, output scoring (LangSmith, Langfuse, Arize Phoenix or OpenTelemetry)

• Systematic prompt optimisation - versioned prompts, A/B tests, DSPy

• Agentic patterns beyond single LLM calls: multi-step orchestration, context management, guardrails and human-in-the-loop

• Retrieval-augmented generation (RAG) and vector search (pgvector, Pinecone), plus frameworks such as LangChain or LangGraph

• Experience with Snowflake or a comparable cloud data warehouse

• Temporal, Socket.IO / WebSockets, Redis, pub/sub

• Working knowledge of React / TypeScript — enough to make small front-end changes when a feature needs them

More reasons to join us

• Flexible working hours and approach to work: fully remotely, in the office or hybrid

• Professional growth supported by internal training sessions and a training budget

• Solid onboarding with a hands-on approach to give you an easy start

• A great atmosphere among professionals who are passionate about their work

• The ability to change the project you work on