Starnavi

About the Project

Our client is building a platform that automates operational data exchange between financial institutions.

Banks, asset managers, and data providers use it to securely reconcile critical information such as user access rights and joiner/leaver events. The platform replaces manual, fragmented processes with automated and secure workflows, reducing operational risk, supporting regulatory compliance, and improving overall efficiency.

In essence, the project modernizes complex back-office operations in the financial sector, making them faster, more accurate, and more reliable.

Your Role

As a Python Developer, you will work on backend services that power these workflows. You will design and maintain APIs, implement business logic, and contribute to building a scalable, reliable system used by financial institutions.

This role is a good fit for engineers who enjoy working on clean backend architecture, well-defined domains, and systems where correctness and stability matter.

Responsibilities

• Develop and maintain backend services using Python
• Build and evolve APIs with Django and FastAPI
• Implement asynchronous and background processing using AsyncIO and Celery
• Work with SQL and NoSQL databases to ensure data integrity and performance
• Collaborate with QA and DevOps to ensure reliable deployments
• Write unit and integration tests as part of regular development
• Participate in code reviews and technical discussions

Requirements

• 3+ years of professional experience with Python
• Strong hands-on experience with Django and FastAPI
• Experience working with AsyncIO and Celery
• Solid understanding of SQL and NoSQL databases
• Familiarity with Docker and containerized environments
• Understanding of HTTP protocol and REST API design principles
• Confidence working in Linux / UNIX environments (shell, scripting, tools)
• You see testing (unit & integration) as part of the creative process, not a chore
• English — Intermediate+ (spoken and written)

Nice to Have

• Experience with fintech or regulated domains
• Background in high-load or data-intensive systems
• Experience with cloud platforms (AWS, Azure, or GCP)

• Experience integrating with Salesforce or similar CRM / third-party enterprise systems

   

Why Starnavi

At Starnavi, you will work on real-world production systems for international clients, collaborate with experienced engineers, and have the opportunity to influence technical decisions. We value responsibility, transparency, and engineering quality.

About the Role

We are looking for a QA Engineer who understands that quality in voice AI is not only about correctness — it’s about timing, flow, and believability.

Our client product involves AI-driven agents that interact with people in real time through voice. These agents handle conversations that include interruptions, ambiguity, background noise, external system calls, and constantly changing context. Your role is to challenge these systems until their weaknesses surface.

This is a hands-on manual QA role, focused on breaking conversational logic, exposing edge cases, and ensuring that AI behavior remains consistent, responsive, and aligned with its intent.

What You Will Do

• Test live voice conversations with AI agents, focusing on responsiveness, interruptions, and natural dialogue pacing
• Validate conversation flows and state changes across multi-step scenarios
• Identify cases where the AI deviates from expected behavior or produces incorrect or fabricated information
• Analyze conversation logic defined in scripted templates and structured data formats
• Verify how the system interacts with external services during a call and how it behaves when those services fail

• Contribute to building reliable test scenarios and reference conversations for regression testing

   

What We Expect

• Experience in manual software testing (1+ year)
• Ability to read and reason about structured logic (e.g. JSON, templated scripts, basic Python)
• Understanding of how voice systems work, including speech recognition, speech synthesis, and silence detection
• Attention to timing issues, edge cases, and non-obvious failure modes
• Curiosity and persistence when testing complex or unpredictable systems

• Fluent Russian and working proficiency in English

   

Nice to Have

• Experience testing chatbots, voice assistants, or call automation systems
• Familiarity with large language models or prompt-based systems
• Background in API or integration testing

About the Role

Our client are developing a platform where AI agents are assembled, configured, and deployed by non-technical users — yet under the surface, these agents rely on deep, carefully engineered logic.

This role sits exactly at that intersection.

You will not be building traditional backends or APIs. Instead, you will design and implement the decision-making layer that defines how AI agents think, react, switch states, and interact with external systems during real conversations.

⚠️ Important clarification:
This is not a Python-first engineering position. While general programming knowledge matters, your daily work will revolve around a custom scripting environment, built on top of Jinja2, used to express complex logic, data transformations, and conversation control. If your primary interest is writing application code in standard frameworks, this role will likely feel uncomfortable. If you enjoy mastering unconventional tools to shape complex system behavior, it will feel rewarding.

What You’ll Be Responsible For

• Designing agent behavior logic
  Build advanced conditional flows, branching paths, and state-aware logic that governs how an AI agent behaves across multi-turn conversations.
• Managing conversation state
  Ensure agents correctly track context, user intent, and system state across interruptions, retries, and edge cases.
• Integrating external systems
  Define how agents exchange data with third-party services (e.g. CRMs, calendars, booking tools) by constructing structured payloads and interpreting responses.
• Creating reusable logic components
  Develop configurable modules that can be reused across many agents by non-technical users without breaking consistency or reliability.

• Troubleshooting and performance tuning
  Investigate unexpected agent behavior (loops, dead ends, incorrect decisions) and optimize logic execution for fast response times in voice-based scenarios.

   

What We’re Looking For

• Strong logical and algorithmic thinking — you are comfortable reasoning about conditions, branching, recursion, and state machines
• Deep experience with templating or embedded logic systems (Jinja2 or similar), including non-trivial data manipulation inside templates
• High confidence working with JSON and complex nested data structures
• Willingness to learn and specialize in a non-standard, proprietary scripting language and become an internal expert

• Ability to work fluently in Russian, with professional-level English

   

Nice to Have

• Experience in solution engineering, implementation roles, or technical consulting
• Background with configuration-driven or low-code systems (e.g. workflow builders, automation platforms)

• Familiarity with Python or other general-purpose languages (for reasoning, not for day-to-day coding)

   

Why This Role Is Unusual

You won’t be shipping endpoints or UI features.
You will be shaping how AI agents reason, decide, and act — in systems where small logic mistakes can break an entire conversation.

If you enjoy building order inside complex, dynamic behavior — this role was designed for you.