Middle Python Developer (part-time)

14 липня 2026

Middle Python Developer (part-time)

віддалено

About the company: Softermii () is an outsourcing/outstaffing company with more than 12 years of experience in web and mobile application development with a team of more than 100 specialists from 6 countries.

We have withstood multiple challenges, such as COVID-19 pandemic and war aggression against Ukraine, we have secured sustainable development processes, saved all our projects and jobs.

Even more — we’re constantly growing. Every day we add new project to our portfolio in the following areas of expertise:

• Healthcare
• Real estate
• Livestream E-commerce
• Fintech (WealthTech, Capital Trading)
• Real-Time Communications (RTC)

In addition, we develop 2 of our own solutions that help our customers get faster applications for video or audio calls () or an application for real estate with 3D visualization ()

Company’s mission: Softermii: Succeed Without (L)imitations We will turn any idea into a valuable product.

Our plans as a company: We want to move from a regular outsourcing business to an ecosystem of outsourcing, education, and product development companies. Over the years, we have arrived at a highly personalized working model with transparent workflows. This model allows us to create software products that meet our clients’ goals with precision. We operate in an AI-assisted development environment, where engineering thinking, logical validation, and responsibility for business outcomes are more important than simply writing code.

About the Role: We are seeking a proactive and skilled Middle Python Developer to join our Engineering team and work on — an AI-driven document analysis tool for the legal industry. In this role, you will be directly responsible for building, optimizing, and scaling backend systems that power our next-generation AI agents.
You will integrate leading LLM APIs, implement multi-agent workflows, and design robust data pipelines to turn complex AI capabilities into reliable, production-ready software.
You’ll join a small, fast-moving team (2 Backend, 1 Frontend, QA, PM) working in a dynamic

Type of cooperation: Remote, Part-time (up to 20 hours per week)

Key Responsibilities:

• AI Agent Development: Design, build, and deploy autonomous and semi-autonomous AI agents capable of reasoning, tool use, and task completion
• LLM API Integration: Integrate and maintain APIs from providers such as OpenAI, Anthropic, Google Gemini, and open-source models
• Orchestration & Frameworks: Implement agentic workflows using modern frameworks
• Backend Architecture: Build high-performance, asynchronous REST/gRPC microservices in Python (FastAPI/AIO to interface between user-facing services and AI models
• Data & Vector Stores: Integrate vector databases (e.g., Qdrant, Pinecone, pgvector) for Retrieval-Augmented Generation (RAG) and memory persistence
• Optimization & Monitoring: Implement observability (tracing, logging, evaluation) for LLM interactions to monitor latency, cost, token usage, and response quality
• Testing & Robustness: Write unit, integration, and evaluation tests to handle model non-determinism, API rate limits, fallback strategies, and structured output validation

Requirements & Qualifications:

• 2-4 years of commercial software development experience with Python
• Strong proficiency with FastAPI, Pydantic, and Asyncio for high-concurrency applications
• Practical experience with SQL (PostgreSQL) and NoSQL/Redis for session management and caching
• Solid understanding of RESTful API design, WebSockets, and event-driven architectures
• Comfortable with Docker, Docker Compose, Git, CI/CD pipelines, and basic cloud deployment (AWS/GCP/Azure)
• Hands-on experience working with LLM APIs (OpenAI Function Calling/Tools, Anthropic Messages API, etc.)
• Understanding of core AI agent patterns (ReAct, Planning, Reflection, Multi-Agent collaboration)
• Experience implementing RAG pipelines, chunking strategies, embeddings, and hybrid search with Vector DBs (Qdrant, pgvector, Weaviate, etc.)
• Experience with at least one major AI orchestration framework (LangGraph, LangChain, LlamaIndex, CrewAI, or custom native implementations)
• Proficiency in enforcing structured data formats from LLMs (via JSON mode, Pydantic Output Parsers, Outlines, or Instructor)
• English — В2.

Nice to Have:

• Experience with LLM observability & evaluation tools
• Familiarity with fine-tuning open-source models
• Background in prompt engineering, guardrails (NeMo Guardrails, Guardrails AI), and AI safety/security (prompt injection defense)
• Knowledge of graph-based state machines (e.g., LangGraph) for complex agent state management

Why You’ll Love This Role:

• State-of-the-art AI work — agentic development is the company’s core driver here, not a side experiment
• Real product impact — you’ll build the AI engine behind a legal-tech document analysis tool, not a toy prototype
• Broad technical exposure — LLM APIs, agent orchestration, vector search, and async backend architecture all in one role

What Makes This Opportunity Special:

• Work at the frontier of agentic AI-driven development as a core company focus, not R&D on the side
• Interesting projects across different business stacks
• Hands-on experience with modern orchestration frameworks and production LLM systems that are becoming industry-essential
• Product-oriented mindset over academic AI experimentation — your work ships and gets used

‍ Who will you have the opportunity to meet during the hiring process (stages): Call, HR, Tech interview, Final interview.

What we can offer you:

• We have stable and highly-functioning processes — everyone has their own role and clear responsibilities, so decisions are made quickly and without unnecessary approvals.
• You will have enough independence to make decisions that can affect not only the project but also the work of the company.
• We are a team of like-minded experts who create interesting products during working hours and enjoy spending free time together.
• Do you have a friend who is currently looking for new job opportunities? Recommend them to us and get a bonus.
• Do you want to volunteer? We will add you to a chat, where we can get a bulletproof vest, buy a pickup truck or send children’s drawings to the front.
• And we have the most empathetic HRs (who also volunteers!). So we are ready to support your well-being in various ways.

‍ A little more information that you may find useful:

• Our adaptation period lasts 3 months — this period of time is enough for us to understand each other better.
• There is a performance review after each year of our collaboration where we use a skills map to track your growth.
• We really have no boundaries in the truest sense of the word — flexible working hours, it’s up to you.

Of course, we have a referral bonus system. So if you have a friend who likes our job opening, you can give us their telegram contact, and we in turn will thank you with a bonus if we start working with them!